Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets

arXiv:2403.17608v1 Announce Type: cross
Abstract: The widespread adoption of generative image models has highlighted the urgent need to detect artificial content, which is a crucial step in combating widespread manipulation and misinformation. Consequently, numerous detectors and associated datasets have emerged. However, many of these datasets inadvertently introduce undesirable biases, thereby impacting the effectiveness and evaluation of detectors. In this paper, we emphasize that many datasets for AI-generated image detection contain biases related to JPEG compression and image size. Using the …

abstract adoption artificial arxiv biases cs.cv cs.lg datasets detection fake generated generative however image image detection manipulation misinformation type